Natural Language Parsing as Statistical Pattern Recognition

TL;DR

This paper introduces an automatic statistical parser that learns from parsed sentences using decision trees, significantly outperforming traditional rule-based parsers in accuracy by leveraging contextual and lexical information.

Contribution

It presents a novel method for automatically acquiring a statistical parser using decision trees, reducing manual effort and improving disambiguation accuracy over traditional grammar-based approaches.

Findings

Decision tree parser achieved 78% accuracy.

Outperformed a ten-year rule-based parser.

Utilized contextual and lexical features for disambiguation.

Abstract

Traditional natural language parsers are based on rewrite rule systems developed in an arduous, time-consuming manner by grammarians. A majority of the grammarian's efforts are devoted to the disambiguation process, first hypothesizing rules which dictate constituent categories and relationships among words in ambiguous sentences, and then seeking exceptions and corrections to these rules. In this work, I propose an automatic method for acquiring a statistical parser from a set of parsed sentences which takes advantage of some initial linguistic input, but avoids the pitfalls of the iterative and seemingly endless grammar development process. Based on distributionally-derived and linguistically-based features of language, this parser acquires a set of statistical decision trees which assign a probability distribution on the space of parse trees given the input sentence. These decision trees take advantage of significant amount of contextual information, potentially including all of the lexical information in the sentence, to produce highly accurate statistical models of the disambiguation process. By basing the disambiguation criteria selection on entropy reduction rather than human intuition, this parser development method is able to consider more sentences than a human grammarian can when making individual disambiguation rules. In experiments between a parser, acquired using this statistical framework, and a grammarian's rule-based parser, developed over a ten-year period, both using the same training material and test sentences, the decision tree parser significantly outperformed the grammar-based parser on the accuracy measure which the grammarian was trying to maximize, achieving an accuracy of 78% compared to the grammar-based parser's 69%.